scholarly journals Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition

2019 ◽  
Vol 33 ◽  
pp. 8610-8617 ◽  
Author(s):  
Hui Li ◽  
Peng Wang ◽  
Chunhua Shen ◽  
Guyu Zhang
Keyword(s):  
State Of The Art ◽  
Text Recognition ◽  
Natural Scene ◽  
Fine Grained ◽  
Word Level ◽  
Scene Text ◽  
Sophisticated Model ◽  
Regular Text ◽  
Algorithm Implementation ◽  
Scene Text Recognition

Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion. Most existing approaches rely heavily on sophisticated model designs and/or extra fine-grained annotations, which, to some extent, increase the difficulty in algorithm implementation and data collection. In this work, we propose an easy-to-implement strong baseline for irregular scene text recognition, using offthe-shelf neural network components and only word-level annotations. It is composed of a 31-layer ResNet, an LSTMbased encoder-decoder framework and a 2-dimensional attention module. Despite its simplicity, the proposed method is robust. It achieves state-of-the-art performance on irregular text recognition benchmarks and comparable results on regular text datasets. The code will be released.

scholarly journals Multi-granularity Deep Local Representations for Irregular Scene Text Recognition

2021 ◽  
Vol 2 (2) ◽  
pp. 1-18
Author(s):  
Hongchao Gao ◽  
Yujia Li ◽  
Jiao Dai ◽  
Xi Wang ◽  
Jizhong Han ◽  
...  
Keyword(s):  
State Of The Art ◽  
Visual Representation ◽  
Text Recognition ◽  
Natural Scene ◽  
Attention Network ◽  
Training Time ◽  
Scene Text ◽  
Benchmark Datasets ◽  
Local Representations ◽  
Scene Text Recognition

Recognizing irregular text from natural scene images is challenging due to the unconstrained appearance of text, such as curvature, orientation, and distortion. Recent recognition networks regard this task as a text sequence labeling problem and most networks capture the sequence only from a single-granularity visual representation, which to some extent limits the performance of recognition. In this article, we propose a hierarchical attention network to capture multi-granularity deep local representations for recognizing irregular scene text. It consists of several hierarchical attention blocks, and each block contains a Local Visual Representation Module (LVRM) and a Decoder Module (DM). Based on the hierarchical attention network, we propose a scene text recognition network. The extensive experiments show that our proposed network achieves the state-of-the-art performance on several benchmark datasets including IIIT-5K, SVT, CUTE, SVT-Perspective, and ICDAR datasets under shorter training time.

scholarly journals Natural Scene Text Recognition Based on Encoder-Decoder Framework

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 62616-62623 ◽  
Author(s):  
Ling-Qun Zuo ◽  
Hong-Mei Sun ◽  
Qi-Chao Mao ◽  
Rong Qi ◽  
Rui-Sheng Jia
Keyword(s):  
Text Recognition ◽  
Natural Scene ◽  
Scene Text ◽  
Scene Text Recognition

Orientation Robust Scene Text Recognition in Natural Scene*

2019 ◽  
Author(s):  
Xiaolong Chen ◽  
Zhengfu Zhang ◽  
Yu Qiao ◽  
Jiangyu Lai ◽  
Jian Jiang ◽  
...  
Keyword(s):  
Text Recognition ◽  
Natural Scene ◽  
Scene Text ◽  
Scene Text Recognition

scholarly journals GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition

2020 ◽  
Vol 34 (07) ◽  
pp. 11005-11012 ◽  
Author(s):  
Wenyang Hu ◽  
Xiaocong Cai ◽  
Jun Hou ◽  
Shuai Yi ◽  
Zhiping Lin
Keyword(s):  
State Of The Art ◽  
Text Recognition ◽  
Convolutional Network ◽  
Attentional Guidance ◽  
Feature Representations ◽  
Lower Accuracy ◽  
Scene Text ◽  
Local Correlations ◽  
Scene Text Recognition ◽  
Connectionist Temporal Classification

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efficient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the benefit of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast inference speed. Moreover, to further leverage the potential of CTC decoder, a graph convolutional network (GCN) is proposed to learn the local correlations of extracted features. Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attention-based methods.

scholarly journals TextScanner: Reading Characters in Order for Robust Scene Text Recognition

2020 ◽  
Vol 34 (07) ◽  
pp. 12120-12127 ◽  
Author(s):  
Zhaoyi Wan ◽  
Minghang He ◽  
Haoran Chen ◽  
Xiang Bai ◽  
Cong Yao
Keyword(s):  
State Of The Art ◽  
Semantic Segmentation ◽  
Text Recognition ◽  
Context Modeling ◽  
Alternative Approach ◽  
Scene Text ◽  
Benchmark Datasets ◽  
Character Position ◽  
Scene Text Recognition ◽  
Character Class

Driven by deep learning and a large volume of data, scene text recognition has evolved rapidly in recent years. Formerly, RNN-attention-based methods have dominated this field, but suffer from the problem of attention drift in certain situations. Lately, semantic segmentation based algorithms have proven effective at recognizing text of different forms (horizontal, oriented and curved). However, these methods may produce spurious characters or miss genuine characters, as they rely heavily on a thresholding procedure operated on segmentation maps. To tackle these challenges, we propose in this paper an alternative approach, called TextScanner, for scene text recognition. TextScanner bears three characteristics: (1) Basically, it belongs to the semantic segmentation family, as it generates pixel-wise, multi-channel segmentation maps for character class, position and order; (2) Meanwhile, akin to RNN-attention-based methods, it also adopts RNN for context modeling; (3) Moreover, it performs paralleled prediction for character position and class, and ensures that characters are transcripted in the correct order. The experiments on standard benchmark datasets demonstrate that TextScanner outperforms the state-of-the-art methods. Moreover, TextScanner shows its superiority in recognizing more difficult text such as Chinese transcripts and aligning with target characters.

scholarly journals 2D Positional Embedding-based Transformer for Scene Text Recognition

2021 ◽  
Vol 6 (1) ◽  
pp. 1-4
Author(s):  
Zobeir Raisi ◽  
Mohamed A. Naiel ◽  
Paul Fieguth ◽  
Steven Wardell ◽  
John Zelek
Keyword(s):  
Spatial Information ◽  
State Of The Art ◽  
Image Features ◽  
Text Recognition ◽  
Recognition Method ◽  
One Dimensional ◽  
Art Scene ◽  
Scene Text ◽  
In The Wild ◽  
Scene Text Recognition

Recent state-of-the-art scene text recognition methods are primarily based on Recurrent Neural Networks (RNNs), however, these methods require one-dimensional (1D) features and are not designed for recognizing irregular-text instances due to the loss of spatial information present in the original two-dimensional (2D) images.  In this paper, we leverage a Transformer-based architecture for recognizing both regular and irregular text-in-the-wild images. The proposed method takes advantage of using a 2D positional encoder with the Transformer architecture to better preserve the spatial information of 2D image features than previous methods. The experiments on popular benchmarks, including the challenging COCO-Text dataset, demonstrate that the proposed scene text recognition method outperformed the state-of-the-art in most cases, especially on irregular-text recognition.

Sign in / Sign up

Export Citation Format

Share Document